Skip to main content

Takes an image or video/stream as input and returns detected faces and emotions.

Project description

IntrospectData's OpenSource FER Application

Give the function an input and it will return a dictionary of detected faces and emotion predictions.


This is a python3 utility for Facial Detection/Emotion Recognition (FER) using Keras and OpenCV.

This project uses the haarcascade xml for facial detection.

We recommend using our model for this application, but you may use your own as well. This project could be easily modified to do other types of object detection if you wish.

If you fork this project, please contribute back with any fixes or features the community may find useful. All PRs will go through a member of our Engineering team.

Please follow GitHub's template for bug reporting.


Note this requires the installation of Tensorflow 2+

Using pip

$ pip3 install fer-capture

From source

$ git clone

$ python3 -m venv env

$ source env/bin/activate

(env) $ pip3 install id_fer_capture

  • To include tensorflow:
    • id-fer_capture[cpu] for cpu based tensorflow
    • id-fer_capture[gpu] for gpu based tensorflow


$ wget -P /path/to/somewhere/

>>> from fer_capture.main import check_stream
>>> from fer_capture.main import check_image
>>> check_stream("/mnt/storage/model.h5", "/mnt/storage/face_test.mp4")
    [{'faces': {...}}, ...]
>>> check_image("/mnt/storage/model.h5", "/mnt/storage/face.jpeg")
    {'faces': {...}}

Append the argument show=True to either function to have a window display. You must press/hold a key for the frame to update in this mode.


Facial Recognition technology is being rapidly adopted by governments and police departments around the world.

With the clear threat to democracy that such technology poses, it is imperative that netizens are able to understand and use similar tech.

That is why we are trying to Democratize the availability of such technology, so that access is not limited to authoritarian actors.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for fer-capture, version 0.2.0
Filename, size File type Python version Upload date Hashes
Filename, size fer_capture-0.2.0-py3-none-any.whl (141.1 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size fer_capture-0.2.0.tar.gz (140.8 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page